{"id":"W4401024942","doi":"10.24963/ijcai.2024/630","title":"SIFAR: A Simple Faster Accelerated Variance-Reduced Gradient Method","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Renmin University of China; National Natural Science Foundation of China; University of Oxford; Royal Society; Institute for Catastrophic Loss Reduction","keywords":"Minimax; Generalization; Mathematical optimization; Mathematics; Saddle point; Stochastic gradient descent; Applied mathematics; Generalization error; Dimension (graph theory); Computer science; Upper and lower bounds; Combinatorics; Artificial intelligence; Artificial neural network; Mathematical analysis","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012004,0.001236325,0.001534389,0.0006704367,0.000453059,0.0008813819,0.001998513,0.00122353,0.006062528],"category_scores_gemma":[0.003088849,0.0005353767,0.0009065221,0.0005492349,0.0007437323,0.001322214,0.001390669,0.001994739,0.002575432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005690912,"about_ca_system_score_gemma":0.001817142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0030697,"about_ca_topic_score_gemma":0.00419851,"domain_scores_codex":[0.9993736,0.0001906038,0.00002417561,0.00008349997,0.0002590623,0.00006903971],"domain_scores_gemma":[0.9992477,0.0003252413,0.00005215596,0.000121724,0.0001943991,0.00005883243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002772136,0.0001740707,0.0007659257,0.0004064281,0.0001638923,0.0002079878,0.0001417649,0.6620491,0.009882415,0.08955857,0.01704328,0.2193294],"study_design_scores_gemma":[0.00003179731,0.00003202113,0.0000429601,0.000009272972,0.000007057264,0.00002739785,0.000005787469,0.9893294,0.00063716,0.00693289,0.002936057,0.000008309685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003005536,0.0002776767,0.9928641,0.0001443159,0.0001007907,0.00004331846,0.00004224793,0.0007960547,0.002725919],"genre_scores_gemma":[0.139097,0.0004757728,0.8503984,0.000470312,0.0001986743,0.0003195656,0.0003955815,0.0008181753,0.007826474],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006062528,"threshold_uncertainty_score":0.0202812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05201765390773348,"score_gpt":0.3303637942119841,"score_spread":0.2783461403042506,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}